Glaucoma Detection Using Visual Geometry Group 22 Model

DOI

10.2991/978-94-6463-716-8_85How to use a DOI?

Keywords

AdaBoost; KNN; SVM; Random Forest; and VGG22; Optic Disc and Cup Segmentation and Ratio; Glaucoma Detection

Abstract

Glaucoma is a degenerative eye illness that, if left untreated, may result in permanent vision loss and blindness. If you have glaucoma, see your eye doctor often. Because early identification and treatment are essential in maintaining one’s eyesight, research into more accurate and effective detection methods for glaucoma is an essential subject. Using photographs of the retinal fundus, machine learning algorithms have shown significant promise as a possible assist in diagnosing glaucoma. In this work, we investigated the ability of five different machine learning algorithms to identify glaucoma from pictures of the retinal fundus: AdaBoost, K-Nearest Neighbor, Support Vector Machine, Random Forest Classifier, and Visual Geometry Group 22(VGG22), a model that was developed for deep learning employed a dataset of 2,870 retinal fundus photographs, including 1500 photos of people with glaucoma and 1370 images of healthy people. The pictures were preprocessed, and then the Optic Disc and Cup Segmentation and Ratio (ODCSR) approach was used to extract their features. We trained and tested all five models using a 10-fold cross-validation procedure, then analyzed their accuracy, precision, recall, and F1-score performance. According to our research findings, VGG22 beat all other models by attaining an overall accuracy of 99.3%. This is compared to the overall accuracy of 89% achieved by Random Forest, 88.1% achieved by SVM, 96.0% achieved by AdaBoost, and 94.4% achieved by KNN. The VGG22 model has superior accuracy, recall, and F1-score performance compared to the other models. In contrast, KNN had the worst accuracy, recall, and F1 score out of all the models.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Upasana Mishra
AU  - Jagdish Raikwal
PY  - 2025
DA  - 2025/05/26
TI  - Glaucoma Detection Using Visual Geometry Group 22 Model
BT  - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)
PB  - Atlantis Press
SP  - 1150
EP  - 1168
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-716-8_85
DO  - 10.2991/978-94-6463-716-8_85
ID  - Mishra2025
ER  -